Graph Neural Networks and Learning Systems

Topic Information

Dear Colleagues,

Learning with graph-structured data, such as molecular, social, biological, and financial networks, requires effective representations of their graph structure. Recently, there has been a surge of interest in graph neural network (GNN) approaches for representation learning of graphs. GNNs typically follow a recursive neighborhood aggregation scheme, where each node aggregates feature vectors of its neighbors to compute its new features. Empirically, GNNs have achieved state-of-the-art performance in many tasks such as learning system function, node classification, link prediction, and graph classification.

The Topic “Graph Neural Networks and Learning Systems” aims to attract cutting-edge research in this fascinating domain. Historically, GNNs have yielded groundbreaking progress in tackling real-world challenges, from anomaly detection to recommender systems, traffic forecasting, disease control, and drug discovery. Despite their rapid emergence and success, the field faces challenges in areas such as fundamental theory and models, algorithms and methods, supporting tools and platforms, and real-world applications. As GNNs have enormous potential applications, this topic is both exciting and controversial. Please join us in creating a diverse collection of articles, and we look forward to receiving your contributions.

Prof. Dr. Huijia Li
Dr. Jun Hu
Dr. Weichen Zhao
Prof. Dr. Jie Cao
Topic Editors

Keywords

Participating Journals

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
Computers computers	4.2	7.5	2012	17.5 Days	CHF 1800
Information information	2.9	6.5	2010	20.9 Days	CHF 1800
AI ai	5.0	6.9	2020	19.2 Days	CHF 1800
Electronics electronics	2.6	6.1	2012	16.4 Days	CHF 2400
Technologies technologies	3.6	8.5	2013	19.1 Days	CHF 1800
Big Data and Cognitive Computing BDCC	4.4	9.8	2017	23.1 Days	CHF 1800

Preprints.org is a multidisciplinary platform offering a preprint service designed to facilitate the early sharing of your research. It supports and empowers your research journey from the very beginning.

MDPI Topics is collaborating with Preprints.org and has established a direct connection between MDPI journals and the platform. Authors are encouraged to take advantage of this opportunity by posting their preprints at Preprints.org prior to publication:

1. Share your research immediately: disseminate your ideas prior to publication and establish priority for your work.
2. Safeguard your intellectual contribution: Protect your ideas with a time-stamped preprint that serves as proof of your research timeline.
3. Boost visibility and impact: Increase the reach and influence of your research by making it accessible to a global audience.
4. Gain early feedback: Receive valuable input and insights from peers before submitting to a journal.
5. Ensure broad indexing: Web of Science (Preprint Citation Index), Google Scholar, Crossref, SHARE, PrePubMed, Scilit and Europe PMC.

Published Papers (3 papers)

Order results

Content type Publication Date

Result details

Normal Extended Compact

Journals

All Computers Information AI Electronics Technologies BDCC

Show export options expand_more Show export options expand_less

Select all

Export citation of selected articles as:

Plain Text BibTeX BibTeX (without abstracts) Endnote Endnote (without abstracts) Tab-delimited RIS

Error

Oops... you haven't selected anything for export.

Ok

clear

19 pages, 1930 KB  

Open AccessArticle

Contamination-Reduced Multi-View Reconstruction for Graph Anomaly Detection

by Qiang Li, Peng Zhang and Qingfeng Tan

Technologies 2026, 14(2), 85; https://doi.org/10.3390/technologies14020085 - 1 Feb 2026

Viewed by 169

Abstract

Graph anomaly detection (GAD) is pivotal for security-critical applications like cybersecurity and financial fraud detection. While reconstruction-based Graph Neural Networks (GNNs) are prevalent, their efficacy is often compromised by two phenomena: (1) anomaly overfitting, where expressive models capture anomalous patterns, and (2) homophily-induced [...] Read more.

Graph anomaly detection (GAD) is pivotal for security-critical applications like cybersecurity and financial fraud detection. While reconstruction-based Graph Neural Networks (GNNs) are prevalent, their efficacy is often compromised by two phenomena: (1) anomaly overfitting, where expressive models capture anomalous patterns, and (2) homophily-induced attenuation, where message passing smooths localized anomaly cues. This paper proposes CLEAN-GAD, a contamination-aware framework that mitigates anomaly influence during training through multi-view robust learning. Specifically, we develop a contrastive augmentation module that utilizes local inconsistency scores to identify and suppress pseudo-anomalous nodes and edges, thereby yielding a purified augmented view. To capture diverse anomaly signals, a frequency-adaptive encoder with dual-pass channels is designed to integrate low- and high-frequency information. Furthermore, we introduce a distribution-separation regularizer and cross-view alignment to stabilize learning and resolve view shifts. Theoretical analysis confirms that reducing the contamination ratio $\rho$ expands the reconstruction-risk gap between normal and anomalous nodes, inherently boosting detection performance. Extensive experiments on multiple benchmark datasets from various domains demonstrate the superior anomaly detection performance of CLEAN-GAD. Full article

(This article belongs to the Topic Graph Neural Networks and Learning Systems)

►▼ Show Figures

Graphical abstract

31 pages, 36598 KB  

Open AccessArticle

Spatio-Temporal and Semantic Dual-Channel Contrastive Alignment for POI Recommendation

by Chong Bu, Yujie Liu, Jing Lu, Manqi Huang, Maoyi Li and Jiarui Li

Big Data Cogn. Comput. 2025, 9(12), 322; https://doi.org/10.3390/bdcc9120322 - 15 Dec 2025

Viewed by 400

Abstract

Point-of-Interest (POI) recommendation predicts users’ future check-ins based on their historical trajectories and plays a key role in location-based services (LBS). Traditional approaches such as collaborative filtering and matrix factorization model user–POI interaction matrices fail to fully leverage spatio-temporal information and semantic attributes, [...] Read more.

Point-of-Interest (POI) recommendation predicts users’ future check-ins based on their historical trajectories and plays a key role in location-based services (LBS). Traditional approaches such as collaborative filtering and matrix factorization model user–POI interaction matrices fail to fully leverage spatio-temporal information and semantic attributes, leading to weak performance on sparse and long-tail POIs. Recently, Graph Neural Networks (GNNs) have been applied by constructing heterogeneous user–POI graphs to capture high-order relations. However, they still struggle to effectively integrate spatio-temporal and semantic information and enhance the discriminative power of learned representations. To overcome these issues, we propose Spatio-Temporal and Semantic Dual-Channel Contrastive Alignment for POI Recommendation (S²DCRec), a novel framework integrating spatio-temporal and semantic information. It employs hierarchical relational encoding to capture fine-grained behavioral patterns and high-level semantic dependencies. The model jointly captures user–POI interactions, temporal dynamics, and semantic correlations in a unified framework. Furthermore, our alignment strategy ensures micro-level collaborative and spatio-temporal consistency and macro-level semantic coherence, enabling fine-grained embedding fusion and interpretable contrastive learning. Experiments on real-world datasets, Foursquare NYC, and Yelp, show that S²DCRec outperforms all baselines, improving F1 scores by 4.04% and 3.01%, respectively. These results demonstrate the effectiveness of the dual-channel design in capturing both sequential and semantic dependencies for accurate POI recommendation. Full article

(This article belongs to the Topic Graph Neural Networks and Learning Systems)

►▼ Show Figures

Figure 1

19 pages, 1247 KB  

Open AccessArticle

Improving News Retrieval with a Learnable Alignment Module for Multimodal Text–Image Matching

by Rui Song, Jiwei Tian, Peican Zhu and Bin Chen

Electronics 2025, 14(15), 3098; https://doi.org/10.3390/electronics14153098 - 3 Aug 2025

Viewed by 2032

Abstract

With the diversification of information retrieval methods, news retrieval tasks have gradually evolved towards multimodal retrieval. Existing methods often encounter issues such as inaccurate alignment and unstable feature matching when handling cross-modal data like text and images, limiting retrieval performance. To address this, [...] Read more.

With the diversification of information retrieval methods, news retrieval tasks have gradually evolved towards multimodal retrieval. Existing methods often encounter issues such as inaccurate alignment and unstable feature matching when handling cross-modal data like text and images, limiting retrieval performance. To address this, this paper proposes an innovative multimodal news retrieval method by introducing the Learnable Alignment Module (LAM), which establishes a learnable alignment relationship between text and images to improve the accuracy and stability of cross-modal retrieval. Specifically, the LAM, through trainable label embeddings (TLEs), enables the text encoder to dynamically adjust category information during training, thereby enhancing the alignment capability of text and images in the shared embedding space. Additionally, we propose three key alignment strategies: logits calibration, parameter consistency, and semantic feature matching, to further optimize the model’s multimodal learning ability. Extensive experiments conducted on four public datasets—Visual News, MMED, N24News, and EDIS—demonstrate that the proposed method outperforms existing state-of-the-art approaches in both text and image retrieval tasks. Notably, the method achieves significant improvements in low-recall scenarios (R@1): for text retrieval, R@1 reaches 47.34, 44.94, 16.47, and 19.23, respectively; for image retrieval, R@1 achieves 40.30, 38.49, 9.86, and 17.95, validating the effectiveness and robustness of the proposed method in multimodal news retrieval. Full article

(This article belongs to the Topic Graph Neural Networks and Learning Systems)

►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less

Select all

Export citation of selected articles as:

Plain Text BibTeX BibTeX (without abstracts) Endnote Endnote (without abstracts) Tab-delimited RIS

 

Error

Oops... you haven't selected anything for export.

Ok

clear

Displaying articles 1-3